Objective:To explore the clinical application value of a combined model based on the radiomics features of magnetic resonance imaging(MRI)and MRI signs in predicting recurrence after radical resection for hepatocellular carcinoma(HCC).Methods:A retrospective analysis was conducted on the imaging data of 100 patients with radical resection for HCC who admitted to Zibo 148 Hospital from May 2016 to May 2020.All patients underwent abdominal enhanced MRI examination before surgery,and they were followed up for at least 2 years after the surgery.They were randomly divided into training group(70 cases)and verification group(30 cases)as a ratio of 7:3.According to the postoperative follow-up results,the training group existed 12 cases of recurrence and 58 cases without recurrence,and the verification group existed 5 cases of recurrence and 25 cases without recurrence.The 3D-slicer software was used to extract radiomics features of preoperative MRI images of each HCC patient.The intra-group correlation coefficient(ICC)of the extracted imaging features of the observers was calculated.The maximum related minimum redundancy(mRMR)algorithm and LASSO regression were selected to analyze the established radiomics labels after dimensionality reduction and screening.Univariate and multivariate logistic regression analysis were used to screen the independent risk factors of predicting recurrence in MRI signs,and they were used respectively to construct radiomics models with the radiomics labels of plain scan,arterial phase,portal phase and hepatobiliary phase.The receiver operating characteristic(ROC)curve was used to assess the diagnostic efficacy of each radiomics model in predicting recurrence.Results:The ICC range of two physicians in selecting radiomics features from the MRI images of all patients were between 0.903 and 0.957,which consistency was favorable(ICC≥0.9).Compared with other predictive models,the highest area under curve(AUC)values of ROC curve of the radiomics model of plain scan of training group[0.951(95%CI:0.901-1.000)]and verification group[0.968(95%CI:0.917-1.000)]were respectively 0.951 and 0.968 in predicting recurrence after radical resection for liver cancer.Conclusion:The combined model that is constructed on the basis of MRI radiomics features has favorable predictive value for the recurrence of patients after radical resection for HCC.Among of them,the radiomics model of plain scan has a certain guiding role in the clinical implementation of personalized treatment plans under the absence of enhancement,and in underdeveloped areas.

Objective To explore the independent risk factors for long-term adverse prognosis after percutaneous renal artery angioplasty in patients with transplant renal artery stenosis(TRAS).Methods We retrospectively collected medical records and surgery details of TRAS patients who underwent renal artery angioplasty at the Department of Peripheral Vascular Diseases,The First Affiliated Hospital of Xi'an Jiaotong University,from January 2017 to June 2021.All patients were followed up for 3 years post-operation.Multivariate Cox regression analyses were performed to find the independent predictive factors for long-term adverse prognosis after renal artery angioplasty in the TRAS patients.Results A total of 45 TRAS patients who underwent percutaneous renal artery angioplasty were included in this study.During the five-year follow-up period,10 patients(22.2％)experienced long-term adverse events.These consisted of 3 patients(6.7％)who died from any cause,1 patient(2.2％)who developed transplant renal artery dissection,6 patients(13.3％)who had restenosis of the transplant renal artery,and 1 patient(2.2％)who lost the transplant kidney and received dialysis again.Multivariate Cox regression analysis showed that male gender(HR=4.915,95％CI:1.036-23.328,P=0.045)and balloon angioplasty alone(HR=8.594,95％CI:2.191-33.710,P=0.002)were independent risk factors for long-term adverse prognosis after renal artery angioplasty in TRAS patients.Conclusion Male gender and balloon angioplasty alone are independent risk factors for long-term adverse prognosis after renal artery angioplasty in TRAS patients.

Objective To investigate the diagnostic accuracy and clinical applicability of the Linknet-VGG16 deep learning algorithm for measuring the effective optical zone(EOZ)after corneal refractive surgery.Methods This single-center retrospective cohort study included 69 patients(69 eyes)who underwent femtosecond laser-assisted in situ kerato-mileusis(FS-LASIK)(34 eyes)or small incision lenticule extraction(SMILE)(35 eyes)at the Refractive Surgery Center of Affiliated Zhengzhou Aier Eye Hospital of Henan University from June 2023 to June 2024.Data from the right eyes of all patients were selected for statistical analysis.During the surgery,patients in the FS-LASIK group adopted the VisuMax fem-tosecond laser system combined with the Amaris 750S excimer laser system,while those in the SMILE group only used the VisuMax femtosecond laser system.A total of 276 Pentacam images were re-examined postoperatively.A Linknet segmenta-tion model based on the VGG16 encoder was constructed,and image normalization techniques were applied to accelerate model convergence.Model performance was assessed using accuracy,intersection over union(IoU),and the Dice coeffi-cient.The traditional EOZ measurement method based on corneal tangential curvature served as the reference standard.Bland-Altman analysis was conducted to evaluate consistency across all images and within each group,and the time effi-ciency of both methods was compared.Results Six representative medical image segmentation architectures(U-Net,U-Net++,DeepLabv3-ResNet50,DeepLabv3+-ResNet50,Unet-Densenet169,and Linknet-VGG16)were systematically evaluated.The Linknet-VGG16 model demonstrated superior performance over the other 5 models in pixel-level accuracy,IoU and Dice coefficient,which were 99.83％,99.48％and 99.74％,respectively.Although there was no significant differ-ence in accuracy and Dice coefficient between Linknet-VGG16 and U-Net models(whose accuracy was 99.82％and Dice coefficient was 99.72％),the inference speed of the U-Net model(62.46 ms)was 31.76％slower than that of the Linknet-VGG16 model(42.62 ms).The evaluation results of a clinically applicable comprehensive scoring model(weights:accura-cy 20％,IoU 20％,Dice coefficient 20％,speed 25％,model size 15％)showed that the Linknet-VGG16 model achieved a score of 88.01,surpassing other architectures(U-Net:86.29;DeepLabv3+-ResNet50:80.41;DeepLabv3-ResNet50:73.82;U-Net++:73.22;Unet-Densenet169:66.66).Bland-Altman analysis revealed that the mean difference of the 136 images in the FS-LASIK group was 0.01 mm[95％limits of agreement(LoA):-0.36 to 0.35 mm],with 96.3％of data points falling within the LoA.The mean difference of the 140 images in the SMILE group was-0.01 mm(95％LoA:-0.36 to 0.33 mum),with 95.7％of data points falling within the LoA.The mean difference of all 276 images was 0.00 mm(95％LoA:-0.36 to 0.34 mm),with 96.4％of data points falling within the LoA.These results indicated excellent consistency.The average measurement time per image using the traditional EOZ measurement method was 13.00 minutes,whereas the deep learning model required only 3.22 seconds.Conclusion The traditional EOZ measurement method based on corne-al tangential curvature exhibits good consistency with the fully automatic EOZ measurement method based on deep learning algorithms,achieving high image recognition accuracy.Additionally,the deep learning algorithm significantly reduces measurement time,compared with the traditional method based on corneal tangential curvature.

Objective To explore the independent risk factors for long-term adverse prognosis after percutaneous renal artery angioplasty in patients with transplant renal artery stenosis(TRAS).Methods We retrospectively collected medical records and surgery details of TRAS patients who underwent renal artery angioplasty at the Department of Peripheral Vascular Diseases,The First Affiliated Hospital of Xi'an Jiaotong University,from January 2017 to June 2021.All patients were followed up for 3 years post-operation.Multivariate Cox regression analyses were performed to find the independent predictive factors for long-term adverse prognosis after renal artery angioplasty in the TRAS patients.Results A total of 45 TRAS patients who underwent percutaneous renal artery angioplasty were included in this study.During the five-year follow-up period,10 patients(22.2％)experienced long-term adverse events.These consisted of 3 patients(6.7％)who died from any cause,1 patient(2.2％)who developed transplant renal artery dissection,6 patients(13.3％)who had restenosis of the transplant renal artery,and 1 patient(2.2％)who lost the transplant kidney and received dialysis again.Multivariate Cox regression analysis showed that male gender(HR=4.915,95％CI:1.036-23.328,P=0.045)and balloon angioplasty alone(HR=8.594,95％CI:2.191-33.710,P=0.002)were independent risk factors for long-term adverse prognosis after renal artery angioplasty in TRAS patients.Conclusion Male gender and balloon angioplasty alone are independent risk factors for long-term adverse prognosis after renal artery angioplasty in TRAS patients.

Objective To investigate the diagnostic accuracy and clinical applicability of the Linknet-VGG16 deep learning algorithm for measuring the effective optical zone(EOZ)after corneal refractive surgery.Methods This single-center retrospective cohort study included 69 patients(69 eyes)who underwent femtosecond laser-assisted in situ kerato-mileusis(FS-LASIK)(34 eyes)or small incision lenticule extraction(SMILE)(35 eyes)at the Refractive Surgery Center of Affiliated Zhengzhou Aier Eye Hospital of Henan University from June 2023 to June 2024.Data from the right eyes of all patients were selected for statistical analysis.During the surgery,patients in the FS-LASIK group adopted the VisuMax fem-tosecond laser system combined with the Amaris 750S excimer laser system,while those in the SMILE group only used the VisuMax femtosecond laser system.A total of 276 Pentacam images were re-examined postoperatively.A Linknet segmenta-tion model based on the VGG16 encoder was constructed,and image normalization techniques were applied to accelerate model convergence.Model performance was assessed using accuracy,intersection over union(IoU),and the Dice coeffi-cient.The traditional EOZ measurement method based on corneal tangential curvature served as the reference standard.Bland-Altman analysis was conducted to evaluate consistency across all images and within each group,and the time effi-ciency of both methods was compared.Results Six representative medical image segmentation architectures(U-Net,U-Net++,DeepLabv3-ResNet50,DeepLabv3+-ResNet50,Unet-Densenet169,and Linknet-VGG16)were systematically evaluated.The Linknet-VGG16 model demonstrated superior performance over the other 5 models in pixel-level accuracy,IoU and Dice coefficient,which were 99.83％,99.48％and 99.74％,respectively.Although there was no significant differ-ence in accuracy and Dice coefficient between Linknet-VGG16 and U-Net models(whose accuracy was 99.82％and Dice coefficient was 99.72％),the inference speed of the U-Net model(62.46 ms)was 31.76％slower than that of the Linknet-VGG16 model(42.62 ms).The evaluation results of a clinically applicable comprehensive scoring model(weights:accura-cy 20％,IoU 20％,Dice coefficient 20％,speed 25％,model size 15％)showed that the Linknet-VGG16 model achieved a score of 88.01,surpassing other architectures(U-Net:86.29;DeepLabv3+-ResNet50:80.41;DeepLabv3-ResNet50:73.82;U-Net++:73.22;Unet-Densenet169:66.66).Bland-Altman analysis revealed that the mean difference of the 136 images in the FS-LASIK group was 0.01 mm[95％limits of agreement(LoA):-0.36 to 0.35 mm],with 96.3％of data points falling within the LoA.The mean difference of the 140 images in the SMILE group was-0.01 mm(95％LoA:-0.36 to 0.33 mum),with 95.7％of data points falling within the LoA.The mean difference of all 276 images was 0.00 mm(95％LoA:-0.36 to 0.34 mm),with 96.4％of data points falling within the LoA.These results indicated excellent consistency.The average measurement time per image using the traditional EOZ measurement method was 13.00 minutes,whereas the deep learning model required only 3.22 seconds.Conclusion The traditional EOZ measurement method based on corne-al tangential curvature exhibits good consistency with the fully automatic EOZ measurement method based on deep learning algorithms,achieving high image recognition accuracy.Additionally,the deep learning algorithm significantly reduces measurement time,compared with the traditional method based on corneal tangential curvature.

Objective:To explore the clinical application value of a combined model based on the radiomics features of magnetic resonance imaging(MRI)and MRI signs in predicting recurrence after radical resection for hepatocellular carcinoma(HCC).Methods:A retrospective analysis was conducted on the imaging data of 100 patients with radical resection for HCC who admitted to Zibo 148 Hospital from May 2016 to May 2020.All patients underwent abdominal enhanced MRI examination before surgery,and they were followed up for at least 2 years after the surgery.They were randomly divided into training group(70 cases)and verification group(30 cases)as a ratio of 7:3.According to the postoperative follow-up results,the training group existed 12 cases of recurrence and 58 cases without recurrence,and the verification group existed 5 cases of recurrence and 25 cases without recurrence.The 3D-slicer software was used to extract radiomics features of preoperative MRI images of each HCC patient.The intra-group correlation coefficient(ICC)of the extracted imaging features of the observers was calculated.The maximum related minimum redundancy(mRMR)algorithm and LASSO regression were selected to analyze the established radiomics labels after dimensionality reduction and screening.Univariate and multivariate logistic regression analysis were used to screen the independent risk factors of predicting recurrence in MRI signs,and they were used respectively to construct radiomics models with the radiomics labels of plain scan,arterial phase,portal phase and hepatobiliary phase.The receiver operating characteristic(ROC)curve was used to assess the diagnostic efficacy of each radiomics model in predicting recurrence.Results:The ICC range of two physicians in selecting radiomics features from the MRI images of all patients were between 0.903 and 0.957,which consistency was favorable(ICC≥0.9).Compared with other predictive models,the highest area under curve(AUC)values of ROC curve of the radiomics model of plain scan of training group[0.951(95%CI:0.901-1.000)]and verification group[0.968(95%CI:0.917-1.000)]were respectively 0.951 and 0.968 in predicting recurrence after radical resection for liver cancer.Conclusion:The combined model that is constructed on the basis of MRI radiomics features has favorable predictive value for the recurrence of patients after radical resection for HCC.Among of them,the radiomics model of plain scan has a certain guiding role in the clinical implementation of personalized treatment plans under the absence of enhancement,and in underdeveloped areas.

Objective: To establish a nomograph model for prediction of cervical central lymph node metastasis (CLNM) among patients with thyroid papillary carcinoma (PTC), so as to provide the evidence for designing personalized treatment plans for PTC. Methods : The data of patients that underwent thyroidectomy and were pathologically diagnosed with PTC post-surgery in the Affiliated Traditional Chinese Medicine Hospital of Xinjiang Medical University from 2018 to 2021 were collected. Patients' data captured from 2018 to 2020 and from 2021 were used as the training set and the validation set, respectively. Predictive factors were screened using a multivariable logistic regression model, and the nomograph model for prediction of CLNM risk was established. The predictive value of the model was evaluated using the receiver operating characteristic (ROC) curve and the adjusted curve. Results: Totally 1 820 PTC cases were included in the training set, including 458 cases with CLNM (25.16%), and 797 cases in the validation set, including 207 cases with CLNM (25.98%). The prediction model is p=ey/(1+ey), y=0.761 + 0.525 × sex + (-0.039) ×age + 0.351 × extrathyroid invasion + 0.368 × neck lymph node enlargement + 1.021×maximum tumor diameter + (-0.009) × TT4 + (-0.001) × anti-TPOAb. The area under the ROC curve was 0.732 for the training set and 0.731 for the validation set, and Hosmer-Lemeshow test showed a good fitting effect (P=0.936, 0.722). Conclusion The nomograph model constructed in this study has a high predictive value for CLNM among patients with PTC.

Objective:To evaluate the efficacy and safety of elbasvir/grazoprevir (EBR/GZR) in patients with genotype 1 chronic hepatitis C in the real-world.Methods:This was an open-label, single-center, retrospective real-world study. A total of 103 genotype 1 chronic hepatitis C patients who were treated with EBR/GZR in Henan Provincial People′s Hospital from May 2018 to October 2019 were enrolled.And the clinical baseline characteristics of patients and the effectiveness and safety of antiviral therapy were respectively evaluated.Results:A total of 103 patients were enrolled in the study with an age of (47.6±13.9) years. Fifty-five (53.4%) patients were male and 48(46.6%) were female. One point nine percent (2/103) patients were genotype 1a hepatitis C and 98.1%(101/103) were genotype 1b hepatitis C. Seventeen genotype 1b hepatitis C patients were previously treated with interferon, and three patients co-infected with hepatitis B virus (HBV). Among the 103 cases, 35 had underlying diseases and 26 had combined medication. Ninty-eight cases completed 12-week treatment and 89 cases completed 12-week follow-up after treatment.Overall, 89 cases achieved sustained virological response. The overall incidence of adverse reactions was 20.4%(21/103), and the main adverse reactions were fatigue, insomnia and anxiety. No serious adverse event occurred. The three patients with HBV co-infection had no hepatitis B activation after treatment.Conclusion:EBR/GZR is effective and safe in the patients with genotype 1 chronic hepatitis C in China.

Objective: To recognize the efficacy and safety of paritaprevir/ritonavir-ombitasvir combined with dasabuvir (OBV/PTV/RTV+DSV) in the treatment of genotype 1b chronic hepatitis C. Methods: Patients with genotype 1b chronic hepatitis C who were admitted to the People's Hospital of Henan Province, Huashan Hospital of Shanghai and the Fifth Medical Center of the General Hospital of the People's Liberation Army of China between November 2017 to August 2018 were enlisted. All patients received OBV/PTV/RTV+DSV antiviral therapy. HCV RNA levels were measured at baseline, weeks 1, 2, 3, 4, 8, 12, and 24, then 12 weeks, and 24 weeks after completion of treatment; patients’ comorbidity, concomitant medications, and clinical adverse events were recorded. Results: 108 patients were enrolled in the study, with an average age of 49.1 years, 44 patients were male (40.8%), 96.3% (104/108) were newly diagnosed, and four patients had previous treatment history, of whom three were treated with IFN and one with IFN + DAA. Ninety-eight cases completed 12 weeks treatment and 89 cases were in follow up for 12 weeks, after discontinuation of the drug. Overall, 89 cases (100%) achieved SVR12.One patient treated with PR and DAA had HCV RNA level of 869175 IU/mL at 4 weeks of treatment, which was significantly higher than the baseline HCV RNA level (301776IU/ML), and was judged as failure of treatment; and follow-up was discontinued. Of all enrolled patients, 19 (17.6%) had underlying diseases and 15 (13.9%) had combined medications. During treatment, adverse events (AE) occurred in 11 patients (10.1%). The main adverse events were pruritus and elevated bilirubin. Conclusion Combined antiviral therapy (OBV/PTV/RTV+DSV) of 12 weeks are highly effective with good safety profile in the treatment of Chinese patients with genotype 1b chronic hepatitis C.